Prompt modification for automated image generation

    公开(公告)号:US12169626B2

    公开(公告)日:2024-12-17

    申请号:US18116003

    申请日:2023-03-01

    Applicant: Snap Inc.

    Abstract: Examples disclosed herein describe prompt modification techniques for automated image generation. An image generation request comprising a base prompt is received from a user device. A plurality of prompt modifiers is identified. A processor-implemented scoring engine determines, for each prompt modifier, a modifier score. The modifier score for each prompt modifier is associated with the base prompt. One or more of the prompt modifiers are automatically selected based on the modifier scores. A modified prompt is generated. The modified prompt is based on the base prompt and the one or more selected prompt modifiers. The modified prompt is provided as input to an automated image generator to generate an image, and the image is caused to be presented on the user device.

    Providing indications of video recording by modifying different interface elements

    公开(公告)号:US12169599B1

    公开(公告)日:2024-12-17

    申请号:US18326706

    申请日:2023-05-31

    Applicant: Snap Inc.

    Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for providing an indication of video recording. The program and method provide for displaying a user interface within an application running on a device, the user interface presenting real-time image data captured by a camera of the device, the user interface including a shutter button which is selectable to initiate video recording in response to a first user gesture; and upon detecting the first user gesture selecting the shutter button, initiating video recording with respect to the real-time image data, replacing a first set of interface elements within the user interface with a second set of interface elements within the user interface, and updating an appearance of the shutter button.

    Diffusers in wearable devices
    103.
    发明授权

    公开(公告)号:US12169325B2

    公开(公告)日:2024-12-17

    申请号:US18207955

    申请日:2023-06-09

    Applicant: Snap Inc.

    Abstract: Eyewear including an optical element, a controller, a support structure configured to support the optical element and the controller, light sources coupled to the controller and supported by the support structure, and a diffuser positioned adjacent to the light sources and supported by the support structure, the diffuser including microstructures that diffuse light emitted by the light sources in a radial anisotropic diffusion pattern or a prism-like diffusion pattern.

    Cellular antenna architectures for AR capable wearable devices

    公开(公告)号:US12166274B2

    公开(公告)日:2024-12-10

    申请号:US17820719

    申请日:2022-08-18

    Applicant: Snap Inc.

    Abstract: Examples include a wearable device having a frame, a temple and onboard electronics components. The frame can optionally configured to hold one or more optical elements. T temple can optionally connected to the frame at a joint such that the temple is disposable between a collapsed condition and a wearable condition in which the wearable device is wearable by a user to hold the one or more optical elements within user view. The onboard electronics components can be carried by at least one of the frame and the temple and can include a first antenna configured for cellular communication carried by the frame and a second antenna configured for cellular communication carried by one of the frame or the temple.

    Navigating through augmented reality content

    公开(公告)号:US12164700B2

    公开(公告)日:2024-12-10

    申请号:US18453019

    申请日:2023-08-21

    Applicant: Snap Inc.

    Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for displaying augmented reality content. The program and method provide for displaying a carousel interface comprising multiple icons, each icon corresponding to a respective one of a plurality of augmented reality content items for displaying with an image captured by a device camera; receiving user input to navigate through display of the plurality of augmented reality content items while displaying the image; and in a case where the user input corresponds to a predefined type of gesture, navigating through display of the plurality of augmented reality content items while displaying the image, and omitting display of the carousel interface.

    MACHINE LEARNING MODEL CONTINUOUS TRAINING SYSTEM

    公开(公告)号:US20240406477A1

    公开(公告)日:2024-12-05

    申请号:US18326724

    申请日:2023-05-31

    Applicant: Snap Inc.

    Abstract: Described is a system for performing a set of machine learning model training operations that include: accessing media content items associated with interaction functions initiated by users of an interaction system, generating training data including labels for the media content items, extracting features from a media content item of the media content items, identifying additional media content items to include in the training data based on the extracted features from the media content item, processing the training data using a machine learning model to generate a media content item output; and updating one or more parameters of the machine learning model based on the media content item output. The system checks whether retraining criteria has been met, and repeats the set of machine learning model training operations to retrain the machine learning model.

    COMPRESSED VIDEO PROCESSING SYSTEM
    107.
    发明申请

    公开(公告)号:US20240404278A1

    公开(公告)日:2024-12-05

    申请号:US18205696

    申请日:2023-06-05

    Applicant: Snap Inc.

    Abstract: Methods and systems are disclosed for applying machine learning models to compressed videos. The system receives a video, depicting an object, that has previously been compressed using one or more video compression processes. The system analyzes, using one or more machine learning models, the video that has previously been compressed to generate a prediction corresponding to the object depicted in the video, with one or more artifacts resulting from application of the one or more machine learning models to the video that has been previously compressed being absent from the prediction. The system generates a visual output based on the prediction in which the one or more artifacts are absent.

    LIFT REPORTING SYSTEM
    108.
    发明申请

    公开(公告)号:US20240403909A1

    公开(公告)日:2024-12-05

    申请号:US18328492

    申请日:2023-06-02

    Applicant: Snap Inc.

    Abstract: A lift reporting system to perform operations that include: accessing user behavior data associated with one or more machine-learned (ML) models, the ML models associated with identifiers; determining causal conversions associated with the ML models based on the user behavior data, the causal conversions comprising values; performing a comparison between the values that represents the causal conversions; determining a ranking of the ML models based on the comparison; and causing display of a graphical user interface (GUI) that includes a display of identifiers associated with ML models.

    Eyewear device input mechanism
    110.
    发明授权

    公开(公告)号:US12160657B2

    公开(公告)日:2024-12-03

    申请号:US18383113

    申请日:2023-10-24

    Applicant: Snap Inc.

    Inventor: Matthew Hanover

    Abstract: An electronics-enabled eyewear device provides a primary command channel and a secondary command channel for receiving user input during untethered wear, one of the command channels providing for tap input detected by motion sensor(s) incorporated in a body of the eyewear device. A predefined tap sequence or pattern can be applied to frame of the device to trigger as device function. In one example, a double tap of the device's frame causes charge level display indicating a battery charge level.

Patent Agency Ranking